forgetDelete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Memory key to delete |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare destructiveHint=true, and readOnlyHint=false, so the agent knows it's destructive. The description adds context by stating the deletion purpose and the kind of data (memories, sensitive data), which goes beyond the annotations. It doesn't mention irreversibility or missing-key behavior, but the idempotentHint covers safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action, and includes usage guidance without unnecessary verbosity. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete-by-key operation, the description is complete: it states the action, key usage, when to use, and companion tools. Annotations cover safety. The lack of output schema is acceptable for a deletion tool. Minor missing detail is the behavior on missing keys, but idempotentHint implies tolerability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter 'key' ('Memory key to delete'), so the schema already provides full meaning. The description only says 'by key', adding no additional detail beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Delete a previously stored memory by key', which is a specific verb (delete) and resource (memory). This distinguishes it from sibling tools remember and recall, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly provides usage guidance: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.' This tells the agent when to use the tool and mentions companion tools, satisfying the 'when vs alternatives' requirement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several groups of tools are hard to tell apart in practice: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and bet_research all route natural-language questions to similar data sources, and the polymarket_* family plus bet_research heavily overlaps. Individual descriptions are detailed, but an agent navigating this surface will frequently struggle to choose the correct entry point.
The naming is readable and mostly snake_case, but conventions are mixed: some tools are verb+noun commands (resolve_entity, validate_claim), some are noun phrases (entity_profile, bet_research), and others use product prefixes inconsistently (ask_pipeworx vs pipeworx_feedback vs polymarket_edges). The polymarket_* cluster is consistent, but no clear pattern holds across the whole server.
34 tools is past the 25-tool threshold and is especially excessive for a server named 'translate', where only three tools relate to translation. Most of the surface belongs to a broad Pipeworx data/analytics/prediction-market platform that would be better split into separate focused servers.
The Pipeworx-related workflows are fairly well-covered: lookup, grounded research, company profiling, prediction-market analysis, subscriptions, and memory all have usable tool clusters. However, the translation domain implied by the server name is thin and references a deepl_translate tool that is not actually exposed, so there is no single domain that feels fully complete.